Where the Score Lives: A Wavelet View of Diffusion

Emma Lucia Byrnes Finn, Binxu Wang, T. Anderson Keller, Demba E. Ba

TL;DR: An analytically solvable wavelet-based score parameterization expresses diffusion scores in terms of data moments, revealing which correlations matter across noise levels.

Abstract: Score-based generative models have had remarkable success over the last decade in generating a diverse set of visually plausible images. A variety of architectures including CNNs, U-Nets, and Transformers have been used as the score-approximation network in such diffusion modeling; however, to date, relatively little is known about how these architectural choices impact generative behavior. In this work, to provide insight into this area, we propose an analytically solvable parameterization of the score function using an expansion in a 2D orthogonal wavelet basis. In particular, we derive interpretable optimal score functions in terms of the moments of the data distribution. We use this parametrization to provide an architecture-agnostic, moment-based analysis that reveals which attributes of the data distribution tend to matter most for denoising. Our score machine is flexible enough to partially mimic the relevant inductive biases of multiple architectures, including U-Nets, and CNNs, taking a step towards understanding why different score architectures can exhibit distinct generative behavior. Since our score is solvable in terms of the moments of the data, we can begin to understand how the data distribution interacts with the score network to produce the behavior we observe in diffusion models.

Code Dataset Promise: No

Format Confirmation: I agree that I have read and followed the formatting instructions for the camera ready version.

Submission Number: 1053